Using Bilinear Models for View-invariant Action and Identity Recognition

Abstract : Human identification from gait is a challenging task in realistic surveillance scenarios in which people walking along arbitrary directions are imaged by a single camera. In this paper, motivated by the view-invariance issue in the human ID from gait problem, we address the general problem of classifying the "content" of human motions of unknown "style". Given a dataset of sequences in which different people walking normally are seen from several wellseparated views, we propose a three-layer scheme based on bilinear models, in which image sequences are mapped to observation vectors of fixed dimension using Markov modeling. We test our approach on the CMU Mobo database, showing how bilinear separation outperforms other approaches, opening the way to view- and action-invariant identity recognition, as well as subject- and view-invariant action recognition.
Type de document :
Communication dans un congrès
Andrew Fitzgibbon and Camillo J. Taylor and Yann LeCun. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '06), Jun 2006, New York, United States. IEEE Computer Society, pp.1701--1708, 2006, 〈10.1109/CVPR.2006.323〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00590209
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:37:34
Dernière modification le : vendredi 6 mai 2011 - 16:24:50

Lien texte intégral

Identifiants

Citation

Fabio Cuzzolin. Using Bilinear Models for View-invariant Action and Identity Recognition. Andrew Fitzgibbon and Camillo J. Taylor and Yann LeCun. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '06), Jun 2006, New York, United States. IEEE Computer Society, pp.1701--1708, 2006, 〈10.1109/CVPR.2006.323〉. 〈inria-00590209〉

Partager

Métriques

Consultations de la notice

25